Attention-Fused Deep Matching Network for Natural Language Inference
Abstract
Natural language inference aims to predict whether a premise sentence can infer another hypothesis sentence. Recent progress on this task only relies on a shallow interaction between sentence pairs, which is insufficient for modeling complex relations. In this paper, we present an attention-fused deep matching network (AF-DMN) for natural language inference. Unlike existing models, AF-DMN takes two sentences as input and iteratively learns the attention-aware representations for each side by multi-level interactions. Moreover, we add a self-attention mechanism to fully exploit local context information within each sentence. Experiment results show that AF-DMN achieves state-of-the-art performance and outperforms strong baselines on Stanford natural language inference (SNLI), multi-genre natural language inference (MultiNLI), and Quora duplicate questions datasets.
Cite
Text
Duan et al. "Attention-Fused Deep Matching Network for Natural Language Inference." International Joint Conference on Artificial Intelligence, 2018. doi:10.24963/IJCAI.2018/561Markdown
[Duan et al. "Attention-Fused Deep Matching Network for Natural Language Inference." International Joint Conference on Artificial Intelligence, 2018.](https://mlanthology.org/ijcai/2018/duan2018ijcai-attention/) doi:10.24963/IJCAI.2018/561BibTeX
@inproceedings{duan2018ijcai-attention,
title = {{Attention-Fused Deep Matching Network for Natural Language Inference}},
author = {Duan, Chaoqun and Cui, Lei and Chen, Xinchi and Wei, Furu and Zhu, Conghui and Zhao, Tiejun},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2018},
pages = {4033-4040},
doi = {10.24963/IJCAI.2018/561},
url = {https://mlanthology.org/ijcai/2018/duan2018ijcai-attention/}
}